Description
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, a frontend-legal multi-request speculative decoding workload can cause the rejection sampler to produce a recovered token equal to the model vocabulary size boundary value, which is then converted to negative one when the engine selects the next live token for a request and is written back into the drafter's input ids; that out-of-vocabulary value is later consumed by the model's embedding and attention path and crashes the engine worker with a GPU device-side assertion. The same triggering request sequence is reachable through the public gRPC Generate and Abort endpoints, so a remote client that can send generation requests can crash the shared engine worker, aborting concurrent requests and causing a service-wide denial of service for other clients of the deployment until the worker is restarted. This issue is fixed in version 0.24.0.
Metrics
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:HWeakness enumeration
Affected software
| Vendor | Product | Versions |
|---|---|---|
| vllm-project | vllm | < 0.24.0 |
References
- https://github.com/vllm-project/vllm/commit/8a5cf1ccd65e8ac7635c402c1ec0b08988bc26caPatch
- https://github.com/vllm-project/vllm/pull/44744Issue Tracking, Patch
- https://github.com/vllm-project/vllm/security/advisories/GHSA-8wr5-jm2h-8r4fVendor Advisory, Exploit
- https://github.com/vllm-project/vllm/security/advisories/GHSA-8wr5-jm2h-8r4fVendor Advisory, Exploit
Timeline
- Published
- Jul 6, 2026
- Last modified
- Oct 25, 2026
- NVD status
- Analyzed